Library
Practical frameworks, patterns, and examples for AI-powered knowledge work.
Principles
Principles
Agent design principles
Seven principles for building AI agents that work reliably in production — consult when designing or debugging an agent system.
Principles
AI output verification
Strategies for validating AI-generated content before use, calibrated to risk — consult when deciding how rigorously to check AI output or when outputs seem unreliable.
Principles
AI productivity traps
Psychological and organizational patterns that cause AI tools to consume time rather than save it — consult when someone feels overwhelmed by AI, is building without clear outcomes, or suspects their AI use is performative.
Principles
Context rot
The systematic degradation of AI accuracy as conversation context grows longer — what causes it, how to detect it, and how to prevent it.
Principles
Productive friction
Framework for deciding when to preserve struggle and challenge rather than automate — consult when evaluating whether a task should be delegated to AI or kept human.
Principles
Spaced practice design
Why short, distributed learning sessions beat long intensive ones, and how to design training formats around that — including managing the frustration spaced practice produces
Methodology
Methodology
Agent use case evaluation
Five-point filter and three-question validation for deciding whether a task is suitable for current-generation AI agent automation — consult before scoping any agent build.
Methodology
AI workflow redesign
Six-phase methodology for transforming existing jobs into AI-native work — consult when helping someone redesign a workflow or identify AI augmentation opportunities.
Methodology
Building agents that hold up
How to evaluate whether a task is suited for AI agent automation, and seven principles for building agents that work reliably in a business context.
Methodology
Choosing an AI assistant
A guided approach to selecting between ChatGPT, Claude, and Gemini using a custom AI advisor that asks about your specific use case, team, and budget.
Methodology
Nate Jones' prompting framework
Nate B Jones' seven-component framework and seven principles for writing structured prompts that get reliable results from high-powered AI models.
Patterns
Patterns
Modes of AI work
Companion framing to the AI scale (chat, context, automation, colleague) that treats the four levels as modes of work — the scale is for your skills, not your workflows. Skills climb the scale once; workflows never climb. Transport metaphor - walk, bike, train, plane; the trip picks the mode. Renamed from "shapes" 2026-07-31.
Patterns
Compound engineering
Practice of building AI workflows that accumulate value through reuse and continuous improvement — consult when designing systems meant to get better over time.
Patterns
PARA method
Four-category organizational system (Projects, Areas, Resources, Archives) for managing all digital information — consult when advising on personal knowledge management or vault structure.
Patterns
Personal agents
Deployment pattern where each team member has their own specialised AI agent rather than a single shared organisational bot — consult when advising on agent rollout strategy, organisational adoption, or how agents change collaboration patterns inside a company.
Patterns
Progressive summarization
Five-layer note-taking technique for making captured knowledge discoverable and useful over time — consult when advising on note-taking or knowledge management practices.
Patterns
Scheduled automation
Pattern for workflows that run on a recurring schedule without human invocation, producing output the human reviews after the fact — covers when to reach for one, the design considerations, and how the pattern shows up in different AI tools
Examples
Examples
Content interview
Custom assistant that interviews the user topic-by-topic about their week and drafts content for multiple channels using a loaded style guide and recent work as material
Examples
Editor agent
Custom assistant that edits text against editorial guidelines while preserving the author's voice
Examples
Email drafter
Custom assistant that drafts emails in the user's voice using loaded style guidelines and relationship context
Examples
End-of-week orchestrator
Multi-stage skill that chains a KPI report, a newsletter insights digest, and a structured reflection waterfall into a single Friday workflow that produces a linked review file
Examples
Image generation with iterative refinement
AI image generation workflow where the AI autonomously iterates on its output until satisfied, then presents for human review
Examples
Inbox processing
Automated content sorting that classifies incoming items and routes them to the right location, escalating when uncertain
Examples
LinkedIn outreach selection
Weekly workflow where AI searches a personal LinkedIn connections export against business context to surface contacts worth reaching out to and drafts angle-specific opening messages
Examples
AI tools monitor
Scheduled weekly run that scans a curated list of sources for new AI tool launches and updates relevant to a target audience, writes a digest, and posts a notification — illustrates the scheduled automation pattern across major AI tools
Examples
Tutorial publish pipeline
Post-production workflow that takes a video tutorial transcript and generates a complete publish package — SEO content, thumbnail, social posts, and a derivative newsletter topic note — in one orchestrated run
Examples
Automated weekly report
Automated KPI dashboard that pulls data from calendar and project management tools to generate progress reports